Multi-response optimization using artificial neural network-based GWO algorithm for high machining performance with minimum quantity lubrication

In the current work, an experimental study has been carried out in order to evaluate the influence of cutting settings on surface roughness and tangential force, when turning of X210Cr12 steel using coated carbide insert with various nose radius. The ANOVA analysis has been performed to determine the effect of cutting conditions on studied outputs. The experimental data have been analyzed using S/N ratios, mean effect graphs, and 3D response surface plots. The results indicate that the cutting insert nose radius and the feed rate are the mainly affecting factors on surface roughness, while tangential force is affected principally by depth of cut followed by feed rate. Confirmatory experiments have been established after Taguchi’s optimization. Mathematical prediction models have been developed using artificial neural network (ANN), and the multi-objective GWO algorithm was integrated for multi-objective optimization of Ra and Fz. It has been found that the cutting force is largely affected by the cutting depth with contribution and feed rate. Also, low feeds and cutting inserts with a large nose are useful for finishing process where low roughness is desired. Regarding the cooling mode, the minimum quantity lubrication is an interesting way to minimize lubricant quantity and protect operator health and environment with keeping better machining quality.